← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
381.6
PP tok/s
48.1
TG tok/s
2684
TTFT (ms)
43.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 381.6 | 48.1 | 43.1 GB | current |
| 4k | 450.1 | 45.8 | 44.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.1 | 1.00× |
| 2× | 63.5 | 1.32× |
| 4× | 86.3 | 1.79× |